cold-email
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and reference data for text generation. No code execution, network requests, or sensitive data access patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill reads from local marketing context files (e.g., .agents/product-marketing.md). While this is a data ingestion surface, the skill only performs text generation based on this data and lacks exploitable capabilities like shell execution or network operations.
- Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md (referenced in SKILL.md).
- Boundary markers: None observed in the instructions.
- Capability inventory: Text generation only; no subprocess calls, file-writes, or network operations detected across any scripts or instructions.
- Sanitization: None observed.
Audit Metadata